mm: Introduce vmap_page_range() to map pages in PCI address space

ioremap_page_range() should be used for ranges within vmalloc range only.
The vmalloc ranges are allocated by get_vm_area(). PCI has "resource"
allocator that manages PCI_IOBASE, IO_SPACE_LIMIT address range, hence
introduce vmap_page_range() to be used exclusively to map pages
in PCI address space.

Fixes: 3e49a86 ("mm: Enforce VM_IOREMAP flag and range in ioremap_page_range.")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://lore.kernel.org/bpf/CANiq72ka4rir+RTN2FQoT=Vvprp_Ao-CvoYEkSNqtSY+RZj+AA@mail.gmail.com

Author: Alexei Starovoitov

arch/arm/mm/ioremap.c

@@ -110,8 +110,8 @@ void __init add_static_vm_early(struct static_vm *svm)
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
-	return ioremap_page_range(virt, virt + PAGE_SIZE, phys,
-				  __pgprot(mtype->prot_pte));
+	return vmap_page_range(virt, virt + PAGE_SIZE, phys,
+			       __pgprot(mtype->prot_pte));
 }
 EXPORT_SYMBOL(ioremap_page);
 
@@ -466,8 +466,8 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 	if (res->end > IO_SPACE_LIMIT)
 		return -EINVAL;
 
-	return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
-				  __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte));
+	return vmap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
+			       __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte));
 }
 EXPORT_SYMBOL(pci_remap_iospace);
 

arch/loongarch/kernel/setup.c

@@ -490,7 +490,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode,
 	}
 
 	vaddr = (unsigned long)(PCI_IOBASE + range->io_start);
-	ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
+	vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
 
 	return 0;
 }

arch/mips/loongson64/init.c

@@ -180,7 +180,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, resource_size_
 
 	vaddr = PCI_IOBASE + range->io_start;
 
-	ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
+	vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
 
 	return 0;
 }

arch/powerpc/kernel/isa-bridge.c

@@ -46,8 +46,8 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size)
 	WARN_ON_ONCE(size & ~PAGE_MASK);
 
 	if (slab_is_available()) {
-		if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
-				pgprot_noncached(PAGE_KERNEL)))
+		if (vmap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+				    pgprot_noncached(PAGE_KERNEL)))
 			vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size);
 	} else {
 		early_ioremap_range(ISA_IO_BASE, pa, size,

drivers/pci/pci.c

@@ -4353,8 +4353,8 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 	if (res->end > IO_SPACE_LIMIT)
 		return -EINVAL;
 
-	return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
-				  pgprot_device(PAGE_KERNEL));
+	return vmap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
+			       pgprot_device(PAGE_KERNEL));
 #else
 	/*
 	 * This architecture does not have memory mapped I/O space,

include/linux/io.h

@@ -23,12 +23,19 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
 #ifdef CONFIG_MMU
 int ioremap_page_range(unsigned long addr, unsigned long end,
 		       phys_addr_t phys_addr, pgprot_t prot);
+int vmap_page_range(unsigned long addr, unsigned long end,
+		    phys_addr_t phys_addr, pgprot_t prot);
 #else
 static inline int ioremap_page_range(unsigned long addr, unsigned long end,
 				     phys_addr_t phys_addr, pgprot_t prot)
 {
 	return 0;
 }
+static inline int vmap_page_range(unsigned long addr, unsigned long end,
+				  phys_addr_t phys_addr, pgprot_t prot)
+{
+	return 0;
+}
 #endif
 
 /*

mm/vmalloc.c

@@ -304,11 +304,24 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end,
 	return err;
 }
 
+int vmap_page_range(unsigned long addr, unsigned long end,
+		    phys_addr_t phys_addr, pgprot_t prot)
+{
+	int err;
+
+	err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
+				 ioremap_max_page_shift);
+	flush_cache_vmap(addr, end);
+	if (!err)
+		err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
+					       ioremap_max_page_shift);
+	return err;
+}
+
 int ioremap_page_range(unsigned long addr, unsigned long end,
 		phys_addr_t phys_addr, pgprot_t prot)
 {
 	struct vm_struct *area;
-	int err;
 
 	area = find_vm_area((void *)addr);
 	if (!area || !(area->flags & VM_IOREMAP)) {
@@ -322,13 +335,7 @@ int ioremap_page_range(unsigned long addr, unsigned long end,
 			  (long)area->addr + get_vm_area_size(area));
 		return -ERANGE;
 	}
-	err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
-				 ioremap_max_page_shift);
-	flush_cache_vmap(addr, end);
-	if (!err)
-		err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
-					       ioremap_max_page_shift);
-	return err;
+	return vmap_page_range(addr, end, phys_addr, prot);
 }
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,